Predicate Grounding on PDDLGym Hanoi Color
100F1 ScoreViLaIn
Evaluation Results
| Method | Links | |
|---|---|---|
| ViLaInBackbone=Gemini 3.1 Flash Lite, Retry Strategy=no retry2026.04 | 100 | |
| ViLaInBackbone=Gemini 3.1 Flash Lite, Retry Strategy=two retries2026.04 | 100 | |
| SYMBOLIZERBackbone=Gemini 3.1 Pro2026.04 | 100 | |
| SYMBOLIZERBackbone=Gemini 3.1 Flash Lite2026.04 | 100 | |
| SYMBOLIZERBackbone=Mistral Small2026.04 | 100 | |
| SymbolizerModel=Mistral Small2026.04 | 88.9 | |
| SymbolizerModel=Gem.3.1-Pro2026.04 | 86.8 | |
| SymbolizerModel=Gem.3.1-FL2026.04 | 84.2 | |
| ViLaInModel=Gem. 3.1-FL, Retries=no retry2026.04 | 80.8 | |
| ViLaInModel=Gem. 3.1-FL, Retries=two retries2026.04 | 79.4 |